Contract role (10–20 hrs/week) to evaluate AI coding agent interactions focusing on usefulness, high-level correctness, engineering judgment, and quality of explanations. Requires staff/principal-level engineering experience, strong familiarity with Python or TypeScript/JavaScript, and experience with tools like OpenAI Codex, Claude Code, or Cursor. Rate $100–$200/hour; duration through early May, start ASAP.

Part-time contract (10–20 hrs/week, through early May) for a senior/staff-level engineer to evaluate end-to-end interactions with AI coding agents (OpenAI Codex, Claude Code, Cursor). Responsibilities include judging usefulness and high-level correctness of outputs, assessing explanations and reasoning, distinguishing response quality levels, and providing clear, opinionated feedback. Rate $100–$200/hour; start ASAP.